INDEX

Explanations

detailed explanations or descriptions within text

oai_token-act-pair · gpt-3.5-turbo

the term "description" and its variations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nuts

-0.79

ced

-0.69

yrus

-0.68

abb

-0.67

cot

-0.66

enthal

-0.66

acus

-0.66

inth

-0.65

ergic

-0.64

lah

-0.62

POSITIVE LOGITS

 descriptions

1.04

 description

1.03

REDACTED

0.86

description

0.83

 synopsis

0.83

 describ

0.82

anguage

0.82

 thereof

0.77

 specifications

0.77

Description

0.75

Activations Density 0.014%

detailed explanations or descriptions within text

the term "description" and its variations

No Comments

No Known Activations